© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37765
    Prev
    Next
    INDEX
    Explanations

    file extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ires
    -0.09
    pal
    -0.09
    azes
    -0.08
    åĶ°
    -0.08
    æĬĬæīĭ
    -0.08
    URI
    -0.08
     Burnett
    -0.08
    fds
    -0.08
    eneral
    -0.08
    BP
    -0.08
    POSITIVE LOGITS
    åľ¨æĪij
    0.10
    asher
    0.09
    amic
    0.09
     Heller
    0.09
    chooser
    0.09
    æĽ¿ä»£
    0.09
    ONES
    0.09
    uxe
    0.09
    anh
    0.09
    lector
    0.09
    Activations Density 0.136%

    No Known Activations